Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms

10/22/2020
by   Alexander Wei, et al.
0

We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust, meaning that the algorithm performs well when predictions are accurate and maintains worst-case guarantees. Such algorithms have been studied in a recent line of works due to Lykouris and Vassilvitskii (ICML '18) and Purohit et al (NeurIPS '18). They provide robustness-consistency trade-offs for a variety of online problems. However, they leave open the question of whether these trade-offs are tight, i.e., to what extent to such trade-offs are necessary. In this paper, we provide the first set of non-trivial lower bounds for competitive analysis using machine-learned predictions. We focus on the classic problems of ski-rental and non-clairvoyant scheduling and provide optimal trade-offs in various settings.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

01/16/2013

Pivotal Pruning of Trade-offs in QPNs

Qualitative probabilistic networks have been designed for probabilistic ...
09/03/2021

Pareto-Optimal Learning-Augmented Algorithms for Online Conversion Problems

This paper leverages machine-learned predictions to design competitive a...
10/16/2019

Adaptive Trade-Offs in Off-Policy Learning

A great variety of off-policy learning algorithms exist in the literatur...
06/25/2020

Practical Trade-Offs for the Prefix-Sum Problem

Given an integer array A, the prefix-sum problem is to answer sum(i) que...
10/26/2018

Quantifying Learning Guarantees for Convex but Inconsistent Surrogates

We study consistency properties of machine learning methods based on min...
11/23/2019

Inflationary Constant Factors and Why Python is Faster Than C++

Constant-factor differences are frequently ignored when analyzing the co...
12/10/2017

Analysis-of-marginal-Tail-Means - a new method for robust parameter optimization

This paper presents a novel method, called Analysis-of-marginal-Tail-Mea...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.